© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 48550
    Prev
    Next
    INDEX
    Explanations

    spinal flexion, fusion, alignment, vertebral devices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    讨
    -0.09
    éĹ®éĹ®
    -0.09
    EditMode
    -0.08
     Tir
    -0.08
    PACE
    -0.08
     resolutions
    -0.08
     ÑĢаÑģÑħод
    -0.08
     Mot
    -0.08
    Mot
    -0.08
    èĥĥèĤł
    -0.08
    POSITIVE LOGITS
    èĥĮ
    0.10
    è´´åIJ§
    0.10
    带头
    0.09
    ä½ķå¿ħ
    0.09
    æī¶æĮģ
    0.09
    StackTrace
    0.09
    主æµģ
    0.09
    æŁģ
    0.08
    èĩ³ä¸Ĭ
    0.08
    edException
    0.08
    Activations Density 0.259%

    No Known Activations